User Requirement Analysis for a Real-Time NLP-Based Open Information Retrieval Meeting Assistant

in Alcaraz, Benoît; Hosseini Kivanani, Nina; Najjar, Amro (Eds.) et al Advances in Information Retrieval (2023, March)

Meetings are recurrent organizational tasks intended to drive progress in an interdisciplinary and collaborative manner. They are, however, prone to inefficiency due to factors such as differing knowledge ... [more ▼]

Meetings are recurrent organizational tasks intended to drive progress in an interdisciplinary and collaborative manner. They are, however, prone to inefficiency due to factors such as differing knowledge among participants. The research goal of this paper is to design a recommendation-based meeting assistant that can improve the efficiency of meetings by helping to contextualize the information being discussed and reduce distractions for listeners. Following a Wizard-of-Oz setup, we gathered user feedback by thematically analyzing focus group discussions and identifying this kind of system’s key challenges and requirements. The findings point to shortcomings in contextualization and raise concerns about distracting listeners from the main content. Based on the findings, we have developed a set of design recommendations that address context, interactivity and personalization issues. These recommendations could be useful for developing a meeting assistant that is tailored to the needs of meeting participants, thereby helping to optimize the meeting experience. [less ▲]

XAI: Using Smart Photobooth for Explaining History of Art

in XAI: Using Smart Photobooth for Explaining History of Art (2022, December)

The rise of Artificial Intelligence has led to advancements in daily life, including applications in industries, telemedicine, farming, and smart cities. It is necessary to have human-AI synergies to ... [more ▼]

The rise of Artificial Intelligence has led to advancements in daily life, including applications in industries, telemedicine, farming, and smart cities. It is necessary to have human-AI synergies to guarantee user engagement and provide interactive expert knowledge, despite AI’s success in "less technical" fields. In this article, the possible synergies between humans and AI to explain the development of art history and artistic style transfer are discussed. This study is part of the "Smart Photobooth" project that is able to automatically transform a user’s picture into a well-known artistic style as an interactive approach to introduce the fundamentals of the history of art to the common people and provide them with a concise explanation of the various art painting styles. This study investigates human-AI synergies by combining the explanation produced by an explainable AI mechanism with a human expert’s insights to provide reasons for school students and a larger audience. [less ▲]

IRRMA: An Image Recommender Robot Meeting Assistant

in IRRMA: An Image Recommender Robot Meeting Assistant (2022, July)

The number of people who attend virtual meetings has increased as a result of COVID-19. In this paper, we present a system that consists of an expressive humanoid social robot called QTRobot, and a ... [more ▼]

The number of people who attend virtual meetings has increased as a result of COVID-19. In this paper, we present a system that consists of an expressive humanoid social robot called QTRobot, and a recommender system that employs natural language processing techniques to recommend images related to the content of the presenter’s speech to the audience in real time. This is achieved utilising the QTRobot’s platform capabilities (microphone, computation power, and Wi-Fi). [less ▲]

Experiments of ASR-based mispronunciation detection for children and adult English learners

in Hosseini Kivanani, Nina; Gretter, Roberto; Matassoni, Marco (Eds.) et al BNAIC/BeneLearn 2021 (2021, November)

Pronunciation is one of the fundamentals of language learning, and it is considered a primary factor of spoken language when it comes to an understanding and being understood by others. The persistent ... [more ▼]

Pronunciation is one of the fundamentals of language learning, and it is considered a primary factor of spoken language when it comes to an understanding and being understood by others. The persistent presence of high error rates in speech recognition domains resulting from mispronunciations motivates us to find alternative techniques for handling mispronunciations. In this study, we develop a mispronunciation assessment system that checks the pronunciation of non-native English speakers, identifies the commonly mispronounced phonemes of Italian learners of English, and presents an evaluation of the non-native pronunciation observed in phonetically annotated speech corpora. In this work, to detect mispronunciations, we used a phone-based ASR implemented using Kaldi. We used two non-native English labeled corpora; (i) a corpus of Italian adults contains 5,867 utterances from 46 speakers, and (ii) a corpus of Italian children consists of 5,268 utterances from 78 children. Our results show that the selected error model can discriminate correct sounds from incorrect sounds in both native and non-native speech, and therefore can be used to detect pronunciation errors in nonnative speech. The phone error rates show improvement in using the error language model. Furthermore, the ASR system shows better accuracy after applying the error model on our selected corpora. [less ▲]